Analisis Klasifikasi Kepuasan Mahasiswa terhadap Pembelajaran Daring menggunakan Algoritma Naive Bayes

Abstract

This study explores the application of the Naive Bayes algorithm in predicting student satisfaction towards online learning. The research process includes data preprocessing, classification, and result evaluation. The dataset comprises 100 instances with 11 attributes, focusing on factors like teaching quality, resource availability, and student interactions. The Naive Bayes algorithm achieved an accuracy of 82%, with key influencing factors identified through Information Gain analysis, such as the study program and interaction quality. The results provide insights into the main factors affecting student satisfaction, offering recommendations for educational institutions to enhance their online learning environments